APA Dictionary of Psychology

in regression analysis, a procedure in which values of 1 or −1 are assigned to represent the categories of a dichotomous variable (or 1, 0, and −1 for a trichotomous variable). The results obtained for the group indicated by values of 1 are then interpreted relative to the larger group comprising all participants. For example, a researcher could assign values of 1 to individuals in an experimental group and values of −1 to those in a control group. They could conclude that there is a treatment effect if the experimental group has a mean different from the grand mean across all of the individuals. Compare contrast coding; dummy variable coding.